Copertina

SemanticZip: A Pilot Framework for Lossy Text Compression with LLMs as Semantic Decompressors

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Trukhina, Natalia, Vashkelis, Vadim
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence Computation and Language Information Retrieval
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Compress the Context, Keep the Commitments: A Formal Framework for Verifiable LLM Context Compression
di: Trukhina, Natalia, et al.
Pubblicazione: (2026)

Unleash LLMs Potential for Recommendation by Coordinating Twin-Tower Dynamic Semantic Token Generator
di: Yin, Jun, et al.
Pubblicazione: (2024)

Hybrid Visual Telemetry for Bandwidth-Constrained Robotic Vision: A Pilot Study with HEVC Base Video and JPEG ROI Stills
di: Trukhina, Natalia, et al.
Pubblicazione: (2026)

Semantic In-Domain Product Identification for Search Queries
di: Sharma, Sanat, et al.
Pubblicazione: (2024)

ComMer: a Framework for Compressing and Merging User Data for Personalization
di: Zeldes, Yoel, et al.
Pubblicazione: (2025)

Query Attribute Modeling: Improving search relevance with Semantic Search and Meta Data Filtering
di: Menon, Karthik, et al.
Pubblicazione: (2025)

Learning Unsupervised Semantic Document Representation for Fine-grained Aspect-based Sentiment Analysis
di: Fu, Hao-Ming, et al.
Pubblicazione: (2024)

RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation
di: Fleischer, Daniel, et al.
Pubblicazione: (2024)

When LLMs are Unfit Use FastFit: Fast and Effective Text Classification with Many Classes
di: Yehudai, Asaf, et al.
Pubblicazione: (2024)

DuoLens: A Framework for Robust Detection of Machine-Generated Multilingual Text and Code
di: Agrawal, Shriyansh, et al.
Pubblicazione: (2025)

SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text
di: He, Weiqing, et al.
Pubblicazione: (2024)

An Iterative Utility Judgment Framework Inspired by Philosophical Relevance via LLMs
di: Zhang, Hengran, et al.
Pubblicazione: (2024)

Knowledge Conflicts for LLMs: A Survey
di: Xu, Rongwu, et al.
Pubblicazione: (2024)

Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation
di: Jung, Dongwon, et al.
Pubblicazione: (2024)

DIVE: Embedding Compression via Self-Limiting Gradient Updates
di: Zhao, Dongfang
Pubblicazione: (2026)

A Comparative Study of Specialized LLMs as Dense Retrievers
di: Zhang, Hengran, et al.
Pubblicazione: (2025)

Beyond RAG: Task-Aware KV Cache Compression for Comprehensive Knowledge Reasoning
di: Corallo, Giulio, et al.
Pubblicazione: (2025)

Quantifying Document Impact in RAG-LLMs
di: Gerami, Armin, et al.
Pubblicazione: (2025)

MacRAG: Compress, Slice, and Scale-up for Multi-Scale Adaptive Context RAG
di: Lim, Woosang, et al.
Pubblicazione: (2025)

SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
di: Zhang, Xuechen, et al.
Pubblicazione: (2025)

Is Implicit Knowledge Enough for LLMs? A RAG Approach for Tree-based Structures
di: Gupte, Mihir, et al.
Pubblicazione: (2025)

LongRecall: A Structured Approach for Robust Recall Evaluation in Long-Form Text
di: Ardestani, MohamamdJavad, et al.
Pubblicazione: (2025)

Do LLMs Understand Collaborative Signals? Diagnosis and Repair
di: Pouryousef, Shahrooz, et al.
Pubblicazione: (2025)

CALRec: Contrastive Alignment of Generative LLMs for Sequential Recommendation
di: Li, Yaoyiran, et al.
Pubblicazione: (2024)

Emotional RAG LLMs: Reading Comprehension for the Open Internet
di: Reichman, Benjamin, et al.
Pubblicazione: (2024)

OpenSanctions Pairs: Large-Scale Entity Matching with LLMs
di: Smith, Chandler, et al.
Pubblicazione: (2026)

MUST-RAG: MUSical Text Question Answering with Retrieval Augmented Generation
di: Kwon, Daeyong, et al.
Pubblicazione: (2025)

KGGen: Extracting Knowledge Graphs from Plain Text with Language Models
di: Mo, Belinda, et al.
Pubblicazione: (2025)

RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs
di: Yu, Yue, et al.
Pubblicazione: (2024)

NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models
di: Lee, Chankyu, et al.
Pubblicazione: (2024)

CKnowEdit: A New Chinese Knowledge Editing Dataset for Linguistics, Facts, and Logic Error Correction in LLMs
di: Fang, Jizhan, et al.
Pubblicazione: (2024)

Exploring the Implicit Semantic Ability of Multimodal Large Language Models: A Pilot Study on Entity Set Expansion
di: Wang, Hebin, et al.
Pubblicazione: (2024)

Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMs
di: Cattaneo, Alberto, et al.
Pubblicazione: (2025)

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play
di: Xu, Ran, et al.
Pubblicazione: (2025)

A Systematic Evaluation of LLM Strategies for Mental Health Text Analysis: Fine-tuning vs. Prompt Engineering vs. RAG
di: Kermani, Arshia, et al.
Pubblicazione: (2025)

UniGLM: Training One Unified Language Model for Text-Attributed Graph Embedding
di: Fang, Yi, et al.
Pubblicazione: (2024)

GraphRAG on Consumer Hardware: Benchmarking Local LLMs for Healthcare EHR Schema Retrieval
di: Fernandes, Peter, et al.
Pubblicazione: (2026)

ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
di: Xu, Peng, et al.
Pubblicazione: (2024)

Using LLMs to discover emerging coded antisemitic hate-speech in extremist social media
di: Kikkisetti, Dhanush, et al.
Pubblicazione: (2024)

The Oracle and The Prism: A Decoupled and Efficient Framework for Generative Recommendation Explanation
di: Zhang, Jiaheng, et al.
Pubblicazione: (2025)